Calculate the TPS of the Arc B570 on local AI models
Every model in our catalogue assessed against this card at the context length and minimum quality you choose. Speed is an estimate for a single request, calculated from this card's memory bandwidth and the size of each model once compressed.
Calculated for this card
Largest model it holds
Ling-lite-1.5 ("Bailing")
16.8B · Q3_K_M · 16.8 tok/s
Fastest model
Gemma 3 QAT 1B
105 tok/s · 1B
What AI models can a Arc B570 run?
Set the inputs, read the answer
More context means more memory for the conversation cache. Speed is for a fresh conversation and does not change with this setting.
Hides models that would only fit by being compressed below this point.
381 models match
Calculating| Quantisation | Fit | ||||||
|---|---|---|---|---|---|---|---|
|
105
tok/s
63–167 · low confidence |
Gemma 3 1B | 1B | Mar 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
105
tok/s
63–167 · low confidence |
Gemma 3 QAT 1B | 1B | Apr 2025 | 1.8 GB | 33k tokens | Q8_0 | Comfortable |
|
105
tok/s
63–167 · low confidence |
HGRN 1B (WT 103) ≈ | 1B | Nov 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
105
tok/s
63–167 · low confidence |
LLama 3..2 Typhoon 2 1B ≈ | 1B | Dec 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
105
tok/s
63–167 · low confidence |
OLMo-1B ≈ | 1B | Feb 2024 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
105
tok/s
63–167 · low confidence |
Pythia-1b ≈ | 1B | Apr 2023 | 1.8 GB | 131k tokens ? | Q8_0 | Comfortable |
|
98.0
tok/s
59–157 · low confidence |
DeepSeekMoE-16B | 16B | Jan 2024 | 8.1 GB | 4k tokens | Q3_K_M | Tight |
|
96.9
tok/s
58–155 · low confidence |
OpenELM-1.1B ≈ | 1.1B | May 2024 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
95.1
tok/s
57–152 · low confidence |
DeciCoder-1B ≈ | 1.1B | Aug 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
95.1
tok/s
57–152 · low confidence |
SantaCoder ≈ | 1.1B | Jan 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
95.1
tok/s
57–152 · low confidence |
TinyLlama-1.1B (1T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
95.1
tok/s
57–152 · low confidence |
TinyLlama-1.1B (3T token checkpoint) ≈ | 1.1B | Oct 2023 | 1.9 GB | 131k tokens ? | Q8_0 | Comfortable |
|
87.2
tok/s
52–139 · low confidence |
EXAONE 4.0 (1.2B) ≈ | 1.2B | Jul 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
87.2
tok/s
52–139 · low confidence |
MinerU2.5 ≈ | 1.2B | Sep 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
87.2
tok/s
52–139 · low confidence |
Pleias 1.0 1.2B ≈ | 1.2B | Dec 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
87.2
tok/s
52–139 · low confidence |
Pleias-RAG-1B ≈ | 1.2B | Apr 2025 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
85.1
tok/s
51–136 · low confidence |
Llama 3.2 1B | 1.2B | Sep 2024 | 2.2 GB | 131k tokens | Q8_0 | Comfortable |
|
83.9
tok/s
50–134 · low confidence |
MiniCPM-1.2B ≈ | 1.2B | Jun 2024 | 2.0 GB | 131k tokens ? | Q8_0 | Comfortable |
|
80.5
tok/s
48–129 · low confidence |
DeepSeek Coder 1.3B ≈ | 1.3B | Jan 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
80.5
tok/s
48–129 · low confidence |
DeepSeek-VL-1.3B ≈ | 1.3B | Mar 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
80.5
tok/s
48–129 · low confidence |
DigiRL ≈ | 1.3B | Jun 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
80.5
tok/s
48–129 · low confidence |
GLA Transformer 1.3B ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
80.5
tok/s
48–129 · low confidence |
Janus 1.3B ≈ | 1.3B | Oct 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
80.5
tok/s
48–129 · low confidence |
Kosmos-2.5 ≈ | 1.3B | Aug 2024 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
|
80.5
tok/s
48–129 · low confidence |
Otter ≈ | 1.3B | May 2023 | 2.1 GB | 131k tokens ? | Q8_0 | Comfortable |
Speeds are estimates for a single request — one conversation at a time — calculated from memory bandwidth, model size and quantisation. Real throughput varies with the inference runtime and its version. Figures published by hardware vendors measure many simultaneous requests and are much higher.
On record
Arc B570 full specification
Everything on record for this board, ordered by how much it bears on running a language model rather than by how a spec sheet would list it. Memory comes first because it decides the outcome; the rest is context.
Memory
The two specifications that decide what this card can run and how quickly. Capacity sets which models fit; bandwidth sets how many tokens per second they produce once they do.
- Memory size
- 10 GB
- Memory bandwidth
- 380 GB/s
- Memory type
- GDDR6
- Memory bus width
- 160 bit
- Memory clock
- 2.38 GHz
The chip
Which processor is on the board and how it was manufactured. A smaller process size generally means more performance for the same power.
- Graphics processor
- BMG-G21
- Architecture
- Xe2-HPG
- Generation
- Battlemage(Arc 5)
- Foundry
- TSMC
- Process size
- 5 nm
- Transistors
- 19.6 billion
- Transistor density
- 72,100 K/mm²
- Die size
- 272 mm²
- Released
- 16 January 2025
Clock speeds
How fast the processor runs. Worth far less here than on a gaming benchmark: generating text is limited by memory bandwidth, so a higher clock barely moves the result.
- Base clock
- 2.5 GHz
- Boost clock
- 2.5 GHz
Processing units
What the chip contains. These drive graphics performance and matter mainly for processing a long prompt rather than for producing the answer.
- Shading units
- 2,304
- Texture mapping units
- 144
- Render output units
- 80
- Ray tracing cores
- 18
- L1 cache
- 250 KB
- L2 cache
- 18 MB
Theoretical performance
Peak arithmetic rates published for the board. These are ceilings that no real workload reaches, and generating text reaches a small fraction of them because it is limited by memory rather than arithmetic.
- Half precision (FP16)
- 23 TFLOPS
- Single precision (FP32)
- 11.5 TFLOPS
- Double precision (FP64)
- 1.4 TFLOPS
- Pixel rate
- 200 GPixel/s
- Texture rate
- 360 GTexel/s
The board
What it takes to physically install and power the card — the practical constraints that decide whether it fits the machine you already own.
- Power draw (TDP)
- 150 W
- Suggested power supply
- 450 W
- Power connectors
- 1x 8-pin
- Bus interface
- PCIe 4.0 x8
- Slot width
- Dual-slot
- Dimensions
- 272 mm
- Display outputs
- 1x HDMI 2.1a, 3x DisplayPort 2.1
Software support
Which graphics and compute interfaces the card supports. CUDA compute capability is the one that bears on inference: below 7.0 there are no tensor cores, and modern inference software falls back to slower code paths.
- DirectX
- 12.2
- OpenGL
- 4.6
- Vulkan
- 1.4
- OpenCL
- 3.0
- Shader model
- 6.6
Listings
Where to buy a Arc B570
No vendor is currently listing this card. Listings come from vendors who publish them here directly — browse the vendor directory to see who is selling what.
What the numbers mean
What the memory subsystem means for AI
Memory
10 GB
Bandwidth
380 GB/s
Largest model
Ling-lite-1.5 ("Bailing")
At 10 GB of GDDR6 the Arc B570 is limited to the smaller end of the catalogue. About 9 GB is actually available to a runtime, and a model has to fit entirely inside it before generating anything at all.
The memory bus moves 380 GB/s across a 160-bit bus. That is the number that governs generation speed — arithmetic per byte read is small enough that the bus, not the cores, is what everything waits on.
The figure is the memory clock — 2.38 GHz here — multiplied by the bus width. It is why core counts predict generation speed so poorly.
Put together, the largest model that fits is Ling-lite-1.5 ("Bailing") at 16.8B, running Q3_K_M and producing around 16.8 tokens per second.
The chip and how it was built
The Arc B570 is built on the BMG-G21 graphics processor, using Intel's Xe2-HPG architecture, as part of the Battlemage(Arc 5) generation.
The chip is manufactured by TSMC, on a 5 nm process, with a die measuring 272 mm², holding 19.6 billion transistors. A smaller process generally means more performance for the same power, though for language models it matters far less than the memory subsystem.
It was released in January 2025, roughly 1 years ago. Inference software support tends to follow hardware by a year or two, so a card of this age generally has mature, well-optimised code paths available to it.
Compute throughput, and why it matters less than it looks
FP16
23 TFLOPS
FP64
1.4 TFLOPS
On paper the Arc B570 reaches 23 TFLOPS at half precision and 11.5 TFLOPS at single precision. These are peak figures no real workload sustains, and generating text reaches only a small fraction of them — decoding is limited by memory rather than arithmetic, which is why a card can look enormously powerful here and still produce tokens at an ordinary rate.
Double-precision throughput is 1.4 TFLOPS. It has no bearing on running a language model — no inference runtime uses it — but it separates datacentre parts from consumer ones, since the latter deliberately restrict it.
Clocks run from 2.5 GHz at base to 2.5 GHz boosted. Worth far less here than on a gaming benchmark: raising the clock speeds up the arithmetic, and the arithmetic is not what generation is waiting on.
Cache and processing units
The Arc B570 has 250 KB of L1 cache, backed by 18 MB of L2. Cache absorbs a share of the memory traffic that would otherwise hit the main bus, which is the one place on this page where a number other than bandwidth quietly affects generation speed — a large L2 lets more of the working set stay close to the cores.
There are 2,304 shading units, 144 texture mapping units, and 80 render output units. These drive graphics workloads and contribute to prompt processing, but they sit idle for much of the time a model spends generating a reply.
Power, size and installation
Power draw
150 W
The Arc B570 is rated at 150 W, with a 450 W power supply suggested for the whole system. Running a language model keeps a card busy in bursts rather than continuously — it draws hard while generating and idles between requests — so sustained draw over a working day is usually well below the rated figure.
The board occupies a dual-slot, measuring 272 mm long, and needs 1x 8-pin. Worth checking against the case and power supply already in the machine, since the largest cards need considerably more of both than a typical desktop provides.
It connects over PCIe 4.0 x8. The interface governs how quickly a model is loaded from disk into the card, not how fast it runs once there, so a narrower link costs a few seconds at startup and nothing thereafter.
The extremes
The largest AI models a Arc B570 can run
The biggest open-weight models that fit on this card, newest first. Each is shown at the best compression the card can hold.
The fastest AI models on a Arc B570
Where this card produces tokens quickest. Smaller models dominate here, because generating each token means reading the whole model out of memory once.
Step by step
How to work out the tokens per second of a Arc B570
You do not have to calculate anything by hand — the gputps.com calculator on this page has already worked it out for every model this card can hold. Reading off the answer takes six steps.
-
01
Start with the model, not the specification
Every one of the 381 models this Arc B570 runs is in the table above. Search narrows it by name or by size.
-
02
Set the context length you will actually use
Longer conversations cost memory on top of the weights. With 10 GB to work in, that is frequently the difference between a model fitting and not.
-
03
Pin the comparison to one quality level
Compression is what lets bigger models fit. The quality control drops any model that needs more of it than you are willing to give.
-
04
Read the speed and the range
The figures are calculated, not measured. 105 tok/s on Gemma 3 QAT 1B is the fastest result on this card, and like every row it carries a range that reflects how much the runtime matters.
-
05
Check the headroom before you decide
Compare what each model needs with the 10 GB this card provides. Tight means it works today; comfortable means it still works when the conversation grows.
-
06
Check the same model from the other side
Every model name in the table links to its own page, which runs the same calculation across every card we hold. That is where you see whether the Arc B570 is the right buy for it or merely a card that fits.
Answers
Arc B570 — common questions
Can a Arc B570 run a 7B model?
Yes. For example a Arc B570 runs DeepSeek Coder 6.7B at Q4_K_M, using about 8.3 GB of memory and generating around 36.1 tokens per second.
Can a Arc B570 run a 13B model?
Yes. For example a Arc B570 runs DeepSeekMoE-16B at Q3_K_M, using about 8.1 GB of memory and generating around 98.0 tokens per second.
How much memory does a Arc B570 have?
A Arc B570 has 10 GB of GDDR6 memory. Around a tenth of that is reserved by the inference runtime and the driver, leaving roughly 9 GB available for a model and its conversation.
What is the memory bandwidth of a Arc B570?
The Arc B570 has 380 GB/s of memory bandwidth, across a 160-bit memory bus. This is the single best predictor of how fast it generates text, because producing each token means reading the entire model out of memory once.
What type of memory does a Arc B570 use?
It uses GDDR6 clocked at 2.38 GHz. HBM types are found on datacentre accelerators and carry far more bandwidth than the GDDR used on desktop cards, which is why they generate tokens considerably faster at the same capacity.
Who makes the Arc B570?
The Arc B570 is a Intel product, with the chip manufactured by TSMC, on a 5 nm process.
When was the Arc B570 released?
The Arc B570 was released in January 2025.
How much power does a Arc B570 use?
The Arc B570 has a rated board power of 150 W, and a 450 W system power supply is suggested. Generating text draws hard in bursts and idles between requests, so average consumption over a working session is normally well below the rated figure.
How much cache does a Arc B570 have?
The Arc B570 has 250 KB of L1 cache, and 18 MB of L2 cache. Cache absorbs part of the memory traffic that would otherwise reach the main bus, so a larger L2 gives a modest lift to generation speed beyond what bandwidth alone predicts.
What are the TFLOPS of a Arc B570?
The Arc B570 is rated at 23 TFLOPS at half precision and 11.5 TFLOPS at single precision. These are peak arithmetic ceilings rather than achievable rates, and text generation reaches only a small fraction of them because it is limited by memory bandwidth instead.
Does the Arc B570 support CUDA?
No. CUDA is NVIDIA-only, and the Arc B570 is a Intel card. It runs language models through ROCm, Vulkan or Metal depending on the software, which are less mature than the CUDA path — our estimates apply a penalty for that.
What bus interface does the Arc B570 use?
It uses PCIe 4.0 x8. This governs how fast a model is loaded onto the card rather than how fast it runs once loaded, so it costs a few seconds at startup and nothing during generation.
Is the Arc B570 good for running local AI models?
Its memory limits it to smaller models though its bandwidth means generation will feel slow on larger models. In total it runs 381 of the models we track. Whether that is enough depends entirely on which model you want — the table above answers that directly.
Can a Arc B570 run a model that does not fit in its memory?
It can be split, with the overflow held in system memory — but that part drags the whole thing down, and none of the 10 GB figures on this page assume it.
Would two Arc B570 cards be twice as fast?
No. A second Arc B570 doubles the memory to 20 GB, which lets you hold models neither could hold alone, but generation does not split that way. These figures describe one card.
What AI models can a Arc B570 run?
381 of the 679 open-weight language models we track fit on a Arc B570 and can be run locally on it. The table on this page lists every one, with the memory it needs, the quantisation it runs at and an estimated generation speed.
What is the largest AI model a Arc B570 can run?
The largest model in our catalogue that fits on a Arc B570 is Ling-lite-1.5 ("Bailing") at 16.8B parameters, compressed to Q3_K_M. It generates roughly 16.8 tokens per second and needs about 8.9 GB of the card's memory.
How many tokens per second does a Arc B570 produce?
It depends on the model. On a Arc B570 the fastest model we track is Gemma 3 QAT 1B at about 105 tokens per second, while larger models run proportionally slower because each token requires reading the whole model out of memory once. Speeds are estimates for a single conversation at a time.
The other direction
Looking at it from the other side?
This page starts from the hardware. If you already know which model you want and need to know what it takes to run it, start from the model instead.